Govern what your AI coding agents do — not just what they say. Runtime policy enforcement for Claude Code, Cursor, Copilot, and more.
Block AI agents from running scripts or touching files outside policy. Linux BPF_LSM, macOS EndpointSecurity, Windows process & file enforcement.
If the policy daemon goes down, agents stop. No silent passthrough. Built for endpoint security, not LLM output filtering.
Three policy archetypes — strict allowlist for lockdown, denylist guardrails for selective blocking, and observe-only mode for staged rollouts.